ABSTRACT
Ever tightening power caps constrain the sustained processing speed of modern processors. With computational sprinting, processors reserve a small power budget that can be used to increase processing speed for short bursts. Computational sprinting speeds up query executions that would otherwise yield slow response time. Common mechanisms used for sprinting include DVFS, core scaling, CPU throttling and application-specific accelerators.
- Songchun Fan, Seyed Majid Zahedi, and Benjamin C. Lee. 2016. The Computational Sprinting Game. In ASPLOS. 561--575.Google Scholar
- Kristen Gardner, Samuel Zbarsky, Sherwin Doroudi, Mor Harchol-Balter, and Esa Hyytiä. 2015. Reducing Latency via Redundant Requests: Exact Analysis. In Sigmetrics. 347--360.Google Scholar
- J. Kelley, C. Stewart, N. Morris, D. Tiwari, Yuxiong He, and S. Elnikety. 2015. Measuring and Managing Answer Quality for Online Data-Intensive Services. In IEEE ICAC.Google Scholar
- Nikita Mishra, John Lafferty, and Henry Hoffmann. 2017. ESP: A Machine Learning Approach to Predicting Application Interference. In International Conference on Autonomic Computing.Google ScholarCross Ref
- Nathaniel Morris, Siva Meenakshi Renganathan, Christopher Stewart, Robert Birke, and Lydia Chen. 2016. Sprint Ability: How Well Does Your Software Exploit Bursts in Processing Capacity?. In International Conference on Autonomic Computing.Google ScholarCross Ref
- Christopher Stewart, Aniket Chakrabarti, and Rean Griffith. 2013. Zoolander: Efficiently Meeting Very Strict, Low-Latency SLOs. In IEEE International Conference on Autonomic Computing.Google Scholar
- Seyed Majid Zahedi, Songchun Fan, Matthew Faw, Elijah Cole, and Benjamin C Lee. 2017. Computational Sprinting: Architecture, Dynamics, and Strategies. ACM Trans, on Computer Systems 34, 4 (2017), 12.Google ScholarDigital Library
- Huazhe Zhang and Henry Hoffmann. 2016. Maximizing Performance Under a Power Cap: A Comparison of Hardware, Software, and Hybrid Techniques. In ASPLOS. 545--559.Google Scholar
Recommendations
Model-driven computational sprinting
EuroSys '18: Proceedings of the Thirteenth EuroSys ConferenceComputational sprinting speeds up query execution by increasing power usage for short bursts. Sprinting policy decides when and how long to sprint. Poor policies inflate response time significantly. We propose a model-driven approach that chooses ...
Computational Sprinting: Architecture, Dynamics, and Strategies
Computational sprinting is a class of mechanisms that boost performance but dissipate additional power. We describe a sprinting architecture in which many, independent chip multiprocessors share a power supply and sprints are constrained by the chips’ ...
Power Modeling for GPU Architectures Using McPAT
Graphics Processing Units (GPUs) are very popular for both graphics and general-purpose applications. Since GPUs operate many processing units and manage multiple levels of memory hierarchy, they consume a significant amount of power. Although several ...
Comments